Production planning and worker training in dynamic manufacturing systems

Production planning is a vital activity in any manufacturing system, and naturally implies assigning the available resources to the required operations. This paper develops and analyzes a comprehensive mathematical model for dynamic manufacturing systems. The proposed model integrates production planning and worker training considering machine and worker time availability, operation sequence and multi-period planning horizon. The objective is to minimize machine maintenance and overhead, system reconfiguration, backorder and inventory holding, training and salary of worker costs. Computational results are presented to verify the proposed model.     

Energy-saving self-configuring networked data centers

In this paper, we develop the optimal minimum-energy scheduler for the dynamic online joint allocation of the task sizes, computing rates, communication rates and communication powers in virtualized Networked Data Centers (NetDCs) that operates under hard per-job delay-constraints. The referred NetDC’s infrastructure is composed by multiple frequency-scalable Virtual Machines (VMs), that are interconnected by a bandwidth and power-limited switched Local Area Network (LAN). Due to the nonlinear power-vs.-communication rate relationship, the resulting Computing-Communication Optimization Problem (CCOP) is inherently nonconvex. In order to analytically compute the exact solution of the CCOP, we develop a solving approach that relies on the following two main steps: (i) we prove that the CCOP retains a loosely coupled structure, that allows us to perform the lossless decomposition of the CCOP into the cascade of two simpler sub-problems; and, (ii) we prove that the coupling between the aforementioned sub-problems is provided by a (scalar) constraint, that is linear in the offered workload. The resulting optimal scheduler is amenable of scalable and distributed online implementation and its analytical characterization is in closed-form. After numerically testing its actual performance under randomly time-varying synthetically generated and real-world measured workload traces, we compare the obtained performance with the corresponding ones of some state-of-the-art static and sequential schedulers.     

A Comparison of Mamdani and Sugeno Fuzzy Based Packet Scheduler for MANET with a Realistic Wireless Propagation Model

 The mobile nature of the nodes in a wireless mobile ad-hoc network (MANET) and the error prone link connectivity between nodes pose many challenges. These include frequent route changes, high packet loss, etc. Such problems increase the end-toend delay and decrease the throughput. This paper proposes two adaptive priority packet scheduling algorithms for MANET based on Mamdani and Sugeno fuzzy inference system. The fuzzy systems consist of three input variables: data rate, signal-to-noise ratio (SNR) and queue size. The fuzzy decision system has been optimised to improve its efficiency. Both fuzzy systems were verified using the Matlab fuzzy toolbox and the performance of both algorithms were evaluated using the riverbed modeler (formally known as OPNET modeler). The results were compared to an existing fuzzy scheduler under various network loads, for constant-bit-rate (CBR) and variable-bit-rate (VBR) traffic. The measuring metrics which form the basis for performance evaluation are end-to-end delay, throughput and packet delivery ratio. The proposed Mamdani and Sugeno scheduler perform better than the existing scheduler for CBR traffic. The end-to-end delay for Mamdani and Sugeno scheduler was reduced by an average of 52% and 54%, respectively. The performance of the throughput and packet delivery ratio for CBR traffic are very similar to the existing scheduler because of the characteristic of the traffic. The network was also at full capacity. The proposed schedulers also showed a better performance for VBR traffic. The end-to-end delay was reduced by an average of 38% and 52%, respectively. Both the throughput and packet delivery ratio (PDR) increased by an average of 53% and 47%, respectively. The Mamdani scheduler is more computationally complex than the Sugeno scheduler, even though they both showed similar network performance. Thus, the Sugeno scheduler is more suitable for real-time applications.     

NN-based Prediction Interval for Nonlinear Processes Controller

Neural networks (NNs) are extensively used in modelling, optimization, and control of nonlinear plants. NN-based inverse type point prediction models are commonly used for nonlinear process control. However, prediction errors (root mean square error (RMSE), mean absolute percentage error (MAPE) etc.) significantly increase in the presence of disturbances and uncertainties. In contrast to point forecast, prediction interval (PI)-based forecast bears extra information such as the prediction accuracy. The PI provides tighter upper and lower bounds with considering uncertainties due to the model mismatch and time dependent or time independent noises for a given confidence level. The use of PIs in the NN controller (NNC) as additional inputs can improve the controller performance. In the present work, the PIs are utilized in control applications, in particular PIs are integrated in the NN internal model-based control framework. A PI-based model that developed using lower upper bound estimation method (LUBE) is used as an online estimator of PIs for the proposed PI-based controller (PIC). PIs along with other inputs for a traditional NN are used to train the PIC to predict the control signal. The proposed controller is tested for two case studies. These include, a chemical reactor, which is a continuous stirred tank reactor (case 1) and a numerical nonlinear plant model (case 2). Simulation results reveal that the tracking performance of the proposed controller is superior to the traditional NNC in terms of setpoint tracking and disturbance rejections. More precisely, 36% and 15% improvements can be achieved using the proposed PIC over the NNC in terms of IAE for case 1 and case 2, respectively for setpoint tracking with step changes.

     

Strength evaluation of granite block samples with different predictive models

Over the last decade, application of soft computing techniques has rapidly grown up in different scientific fields, especially in rock mechanics. One of these cases relates to indirect assessment of uniaxial compressive strength (UCS) of rock samples with different artificial intelligent-based methods. In fact, the main advantage of such systems is to readily remove some difficulties arising in direct assessment of UCS, such as time-consuming and costly UCS test procedure. This study puts an effort to propose four accurate and practical predictive models of UCS using artificial neural network (ANN), hybrid ANN with imperialism competitive algorithm (ICA–ANN), hybrid ANN with artificial bee colony (ABC–ANN) and genetic programming (GP) approaches. To reach the aim of the current study, an experimental database containing a total of 71 data sets was set up by performing a number of laboratory tests on the rock samples collected from a tunnel site in Malaysia. To construct the desired predictive models of UCS based on training and test patterns, a combination of several rock characteristics with the most influence on UCS has been used as input parameters, i.e. porosity (n), Schmidt hammer rebound number (R), p-wave velocity (V_p) and point load strength index (Is(50)). To evaluate and compare the prediction precision of the developed models, a series of statistical indices, such as root mean squared error (RMSE), determination coefficient (R²) and variance account for (VAF) are utilized. Based on the simulation results and the measured indices, it was observed that the proposed GP model with the training and test RMSE values 0.0726 and 0.0691, respectively, gives better performance as compared to the other proposed models with values of (0.0740 and 0.0885), (0.0785 and 0.0742), and (0.0746 and 0.0771) for ANN, ICA–ANN and ABC–ANN, respectively. Moreover, a parametric analysis is accomplished on the proposed GP model to further verify its generalization capability. Hence, this GP-based model can be considered as a new applicable equation to accurately estimate the uniaxial compressive strength of granite block samples.

     

A novel approach to predict shear strength of tilted angle connectors using artificial intelligence techniques

Shear connectors play a prominent role in the design of steel-concrete composite systems. The behavior of shear connectors is generally determined through conducting push-out tests. However, these tests are costly and require plenty of time. As an alternative approach, soft computing (SC) can be used to eliminate the need for conducting push-out tests. This study aims to investigate the application of artificial intelligence (AI) techniques, as sub-branches of SC methods, in the behavior prediction of an innovative type of C-shaped shear connectors, called Tilted Angle Connectors. For this purpose, several push-out tests are conducted on these connectors and the required data for the AI models are collected. Then, an adaptive neuro-fuzzy inference system (ANFIS) is developed to identify the most influencing parameters on the shear strength of the tilted angle connectors. Totally, six different models are created based on the ANFIS results. Finally, AI techniques such as an artificial neural network (ANN), an extreme learning machine (ELM), and another ANFIS are employed to predict the shear strength of the connectors in each of the six models. The results of the paper show that slip is the most influential factor in the shear strength of tilted connectors and after that, the inclination angle is the most effective one. Moreover, it is deducted that considering only four parameters in the predictive models is enough to have a very accurate prediction. It is also demonstrated that ELM needs less time and it can reach slightly better performance indices than those of ANN and ANFIS.

     

Full-state neural network observer-based hybrid quantum diagonal recurrent neural network adaptive tracking control

Neural Computing and Applications - This study introduces a neural network (NN) adaptive tracking controller-based reinforcement learning (RL) scheme for unknown nonlinear systems. First, an...     

Improved crossover firefly algorithm based deep Beleif network for low-resolution face recognition

Multimedia Tools and Applications - Face detection by low-resolution image (LR) is one of the key aspects of Human-Computer Interaction(HCI). Due to the LR image, which has changes in pose,...     

Detection of individual activities in video sequences based on fast interference discovery and semi-supervised method

Multimedia Tools and Applications - Auto understanding of human activities in video is an increasing necessity in some application realms. The existing methods for human’s activity...